arXiv subjects

Bani Mallick

Publications and source records attributed to Bani Mallick.

11 recordsLinked to original sources

arXiv2026

On Graph-Informed Distance Metrics for Comparing Graph Partitions

Comparing graph partitions is fundamental to the analysis of network-structured data, yet existing measures for comparing graph partitions typically rely on graph-agnostic indices that treat vertices as exchangeable, ignoring the underlying graph topology that encodes essential information about community cohesion and separation. We propose a general construction of graph-informed distances that compares vertex partitions through induced edge partitions and yields valid metrics on the space of contiguous graph partitions. As special cases, we develop graph-informed versions of variation of information and the van Dongen distance together with a binary cut-based companion distance, and show that these distances satisfy a natural local graph-aware refinement criterion. Under stochastic block models, we prove that stronger topological disruptions incur asymptotically larger distances almost surely in both inter-community and intra-community split settings. These results provide a simple and principled framework to compare graph partitions while respecting the underlying graph structure.

stat.ME↗

arXiv2024

Embracing Unknown Step by Step: Towards Reliable Sparse Training in Real World

Sparse training has emerged as a promising method for resource-efficient deep neural networks (DNNs) in real-world applications. However, the reliability of sparse models remains a crucial concern, particularly in detecting unknown out-of-distribution (OOD) data. This study addresses the knowledge gap by investigating the reliability of sparse training from an OOD perspective and reveals that sparse training exacerbates OOD unreliability. The lack of unknown information and the sparse constraints hinder the effective exploration of weight space and accurate differentiation between known and unknown knowledge. To tackle these challenges, we propose a new unknown-aware sparse training method, which incorporates a loss modification, auto-tuning strategy, and a voting scheme to guide weight space exploration and mitigate confusion between known and unknown information without incurring significant additional costs or requiring access to additional OOD data. Theoretical insights demonstrate how our method reduces model confidence when faced with OOD samples. Empirical experiments across multiple datasets, model architectures, and sparsity levels validate the effectiveness of our method, with improvements of up to \textbf{8.4\%} in AUROC while maintaining comparable or higher accuracy and calibration. This research enhances the understanding and readiness of sparse DNNs for deployment in resource-limited applications. Our code is available on: \url{https://github.com/StevenBoys/MOON}.

cs.LG↗

arXiv2024

Integrative Variational Autoencoders for Generative Modeling of an Image Outcome with Multiple Input Images

Understanding relationships across multiple imaging modalities is central to neuroimaging research. We introduce the Integrative Variational Autoencoder (InVA), the first hierarchical VAE framework for image-on-image regression in multimodal neuroimaging. Unlike standard VAEs, which are not designed for predictive integration across modalities, InVA models outcome images as functions of both shared and modality-specific features. This flexible, data-driven approach avoids rigid assumptions of classical tensor regression and outperforms conventional VAEs and nonlinear models such as BART. As a key application, InVA accurately predicts costly PET scans from structural MRI, offering an efficient and powerful tool for multimodal neuroimaging.

eess.IV↗

arXiv2023

Adaptive Conditional Quantile Neural Processes

Neural processes are a family of probabilistic models that inherit the flexibility of neural networks to parameterize stochastic processes. Despite providing well-calibrated predictions, especially in regression problems, and quick adaptation to new tasks, the Gaussian assumption that is commonly used to represent the predictive likelihood fails to capture more complicated distributions such as multimodal ones. To overcome this limitation, we propose Conditional Quantile Neural Processes (CQNPs), a new member of the neural processes family, which exploits the attractive properties of quantile regression in modeling the distributions irrespective of their form. By introducing an extension of quantile regression where the model learns to focus on estimating informative quantiles, we show that the sampling efficiency and prediction accuracy can be further enhanced. Our experiments with real and synthetic datasets demonstrate substantial improvements in predictive performance compared to the baselines, and better modeling of heterogeneous distributions' characteristics such as multimodality.

cs.LG↗

arXiv2023

Calibrating the Rigged Lottery: Making All Tickets Reliable

Although sparse training has been successfully used in various resource-limited deep learning tasks to save memory, accelerate training, and reduce inference time, the reliability of the produced sparse models remains unexplored. Previous research has shown that deep neural networks tend to be over-confident, and we find that sparse training exacerbates this problem. Therefore, calibrating the sparse models is crucial for reliable prediction and decision-making. In this paper, we propose a new sparse training method to produce sparse models with improved confidence calibration. In contrast to previous research that uses only one mask to control the sparse topology, our method utilizes two masks, including a deterministic mask and a random mask. The former efficiently searches and activates important weights by exploiting the magnitude of weights and gradients. While the latter brings better exploration and finds more appropriate weight values by random updates. Theoretically, we prove our method can be viewed as a hierarchical variational approximation of a probabilistic deep Gaussian process. Extensive experiments on multiple datasets, model architectures, and sparsities show that our method reduces ECE values by up to 47.8\% and simultaneously maintains or even improves accuracy with only a slight increase in computation and storage burden.

cs.LG↗

arXiv2022

Ordinal Causal Discovery

Causal discovery for purely observational, categorical data is a long-standing challenging problem. Unlike continuous data, the vast majority of existing methods for categorical data focus on inferring the Markov equivalence class only, which leaves the direction of some causal relationships undetermined. This paper proposes an identifiable ordinal causal discovery method that exploits the ordinal information contained in many real-world applications to uniquely identify the causal structure. The proposed method is applicable beyond ordinal data via data discretization. Through real-world and synthetic experiments, we demonstrate that the proposed ordinal causal discovery method combined with simple score-and-search algorithms has favorable and robust performance compared to state-of-the-art alternative methods in both ordinal categorical and non-categorical data. An accompanied R package OrdCD is freely available on CRAN and at https://web.stat.tamu.edu/~yni/files/OrdCD_1.0.0.tar.gz.

stat.ME↗

arXiv2021

Off-Policy Evaluation Using Information Borrowing and Context-Based Switching

We consider the off-policy evaluation (OPE) problem in contextual bandits, where the goal is to estimate the value of a target policy using the data collected by a logging policy. Most popular approaches to the OPE are variants of the doubly robust (DR) estimator obtained by combining a direct method (DM) estimator and a correction term involving the inverse propensity score (IPS). Existing algorithms primarily focus on strategies to reduce the variance of the DR estimator arising from large IPS. We propose a new approach called the Doubly Robust with Information borrowing and Context-based switching (DR-IC) estimator that focuses on reducing both bias and variance. The DR-IC estimator replaces the standard DM estimator with a parametric reward model that borrows information from the 'closer' contexts through a correlation structure that depends on the IPS. The DR-IC estimator also adaptively interpolates between this modified DM estimator and a modified DR estimator based on a context-specific switching rule. We give provable guarantees on the performance of the DR-IC estimator. We also demonstrate the superior performance of the DR-IC estimator compared to the state-of-the-art OPE algorithms on a number of benchmark problems.

stat.ML↗

arXiv2021

Spline-Based Bayesian Emulators for Large Scale Spatial Inverse Problems

A Bayesian approach to nonlinear inverse problems is considered where the unknown quantity (input) is a random spatial field. The forward model is complex and non-linear, therefore computationally expensive. An emulator-based methodology is developed, where the Bayesian multivariate adaptive regression splines (BMARS) are used to model the function that maps the inputs to the outputs. Discrete cosine transformation (DCT) is used for dimension reduction of the input spatial field. The posterior sampling is carried out using trans-dimensional Markov Chain Monte Carlo (MCMC) methods. Numerical results are presented by analyzing simulated as well as real data on hydrocarbon reservoir characterization.

stat.AP↗

arXiv2020

Probabilistic Hosting Capacity Analysis via Bayesian Optimization

This paper studies the probabilistic hosting capacity analysis (PHCA) problem in distribution networks considering uncertainties from distributed energy resources (DERs) and residential loads. PHCA aims to compute the hosting capacity, which is defined as the maximal level of DERs that can be securely integrated into a distribution network while satisfying operational constraints with high probability. We formulate PHCA as a chance-constrained optimization problem, and model the uncertainties from DERs and loads using historical data. Due to non-convexities and a substantial number of historical scenarios being used, PHCA is often formulated as large-scale nonlinear optimization problem, thus computationally intractable to solve. To address the core computational challenges, we propose a fast and extensible framework to solve PHCA based on Bayesian Optimization (BayesOpt). Comparing with state-of-the-art algorithms such as interior point and active set, numerical results show that the proposed BayesOpt approach is able to find better solutions (25% higher hosting capacity) with 70% savings in computation time on average.

eess.SY↗

arXiv2019

Bayesian Graph Selection Consistency Under Model Misspecification

Gaussian graphical models are a popular tool to learn the dependence structure in the form of a graph among variables of interest. Bayesian methods have gained in popularity in the last two decades due to their ability to simultaneously learn the covariance and the graph and characterize uncertainty in the selection. For scalability of the Markov chain Monte Carlo algorithms, decomposability is commonly imposed on the graph space. A wide variety of graphical conjugate priors are proposed jointly on the covariance matrix and the graph with improved algorithms to search along the space of decomposable graphs, rendering the methods extremely popular in the context of multivariate dependence modeling. {\it An open problem} in Bayesian decomposable structure learning is whether the posterior distribution is able to select a meaningful decomposable graph that it is ``close'' in an appropriate sense to the true non-decomposable graph, when the dimension of the variables increases with the sample size. In this article, we explore specific conditions on the true precision matrix and the graph which results in an affirmative answer to this question using a commonly used hyper-inverse Wishart prior on the covariance matrix and a suitable complexity prior on the graph space, both in the well-specified and misspecified settings. In absence of structural sparsity assumptions, our strong selection consistency holds in a high dimensional setting where $p = O(n^α)$ for $α< 1/3$. We show when the true graph is non-decomposable, the posterior distribution on the graph concentrates on a set of graphs that are {\it minimal triangulations} of the true graph.

math.ST↗

arXiv2011

A Bayesian Approach to Detection of Small Low Emission Sources

The article addresses the problem of detecting presence and location of a small low emission source inside of an object, when the background noise dominates. This problem arises, for instance, in some homeland security applications. The goal is to reach the signal-to-noise ratio (SNR) levels on the order of $10^{-3}$. A Bayesian approach to this problem is implemented in 2D. The method allows inference not only about the existence of the source, but also about its location. We derive Bayes factors for model selection and estimation of location based on Markov Chain Monte Carlo (MCMC) simulation. A simulation study shows that with sufficiently high total emission level, our method can effectively locate the source.

math.ST↗